Topological Preservation in Temporal Link Prediction

Marco Campos, Casey Doyle, Daniel Krofcheck, Sarah Simpson, Michael Xi, William Ott, Henry Adams
Proceedings of the 1st Conference on Topology, Algebra, and Geometry in Data Science(TAG-DS 2025), PMLR 321:56-78, 2026.

Abstract

Temporal link prediction seeks to model evolving networks to forecast future or missing interactions. Although many methods in this field achieve strong predictive performance, interpretability remains limited, especially in high-stakes domains. We address this by showing how topological data analysis can assess the faithfulness of learned representations to the underlying data, providing a pipeline for comparing temporal topological structure across modal output. We further introduce a prototypical model that enables this analysis while maintaining predictive power. Taken together, these contributions lay the groundwork for models whose representations are more transparent to end users.

Cite this Paper

BibTeX
@InProceedings{pmlr-v321-campos26a, title = {Topological Preservation in Temporal Link Prediction}, author = {Campos, Marco and Doyle, Casey and Krofcheck, Daniel and Simpson, Sarah and Xi, Michael and Ott, William and Adams, Henry}, booktitle = {Proceedings of the 1st Conference on Topology, Algebra, and Geometry in Data Science(TAG-DS 2025)}, pages = {56--78}, year = {2026}, editor = {Bernardez Gil, Guillermo and Black, Mitchell and Cloninger, Alexander and Doster, Timothy and Emerson, Tegan and Garcı́a-Rodondo, Ińes and Holtz, Chester and Kotak, Mit and Kvinge, Henry and Mishne, Gal and Papillon, Mathilde and Pouplin, Alison and Rainey, Katie and Rieck, Bastian and Telyatnikov, Lev and Yeats, Eric and Wang, Qingsong and Wang, Yusu and Wayland, Jeremy}, volume = {321}, series = {Proceedings of Machine Learning Research}, month = {01--02 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v321/main/assets/campos26a/campos26a.pdf}, url = {https://proceedings.mlr.press/v321/campos26a.html}, abstract = {Temporal link prediction seeks to model evolving networks to forecast future or missing interactions. Although many methods in this field achieve strong predictive performance, interpretability remains limited, especially in high-stakes domains. We address this by showing how topological data analysis can assess the faithfulness of learned representations to the underlying data, providing a pipeline for comparing temporal topological structure across modal output. We further introduce a prototypical model that enables this analysis while maintaining predictive power. Taken together, these contributions lay the groundwork for models whose representations are more transparent to end users.} }
Endnote
%0 Conference Paper %T Topological Preservation in Temporal Link Prediction %A Marco Campos %A Casey Doyle %A Daniel Krofcheck %A Sarah Simpson %A Michael Xi %A William Ott %A Henry Adams %B Proceedings of the 1st Conference on Topology, Algebra, and Geometry in Data Science(TAG-DS 2025) %C Proceedings of Machine Learning Research %D 2026 %E Guillermo Bernardez Gil %E Mitchell Black %E Alexander Cloninger %E Timothy Doster %E Tegan Emerson %E Ińes Garcı́a-Rodondo %E Chester Holtz %E Mit Kotak %E Henry Kvinge %E Gal Mishne %E Mathilde Papillon %E Alison Pouplin %E Katie Rainey %E Bastian Rieck %E Lev Telyatnikov %E Eric Yeats %E Qingsong Wang %E Yusu Wang %E Jeremy Wayland %F pmlr-v321-campos26a %I PMLR %P 56--78 %U https://proceedings.mlr.press/v321/campos26a.html %V 321 %X Temporal link prediction seeks to model evolving networks to forecast future or missing interactions. Although many methods in this field achieve strong predictive performance, interpretability remains limited, especially in high-stakes domains. We address this by showing how topological data analysis can assess the faithfulness of learned representations to the underlying data, providing a pipeline for comparing temporal topological structure across modal output. We further introduce a prototypical model that enables this analysis while maintaining predictive power. Taken together, these contributions lay the groundwork for models whose representations are more transparent to end users.
APA
Campos, M., Doyle, C., Krofcheck, D., Simpson, S., Xi, M., Ott, W. & Adams, H.. (2026). Topological Preservation in Temporal Link Prediction. Proceedings of the 1st Conference on Topology, Algebra, and Geometry in Data Science(TAG-DS 2025), in Proceedings of Machine Learning Research 321:56-78 Available from https://proceedings.mlr.press/v321/campos26a.html.

Related Material